you can give "unloading some layers to RAM" a try though.. that way you can get your hands on the "usable" 31b models. browse around to find some good 31b ones.. GL
- Posts
- 12
- Comments
- 57
- Joined
- 1 yr. ago
- Posts
- 12
- Comments
- 57
- Joined
- 1 yr. ago
LocalLLaMA @sh.itjust.works My experience with local LLM
Blogging @programming.dev Networking / reach platform
Fediverse @lemmy.world better Mastodon feeds
No Stupid Questions (Developer Edition) @programming.dev Income stream from developer sideblog?
Blogging @programming.dev Income stream from developer sideblog?
Electronics @discuss.tchncs.de critique for programming guide for cortex-M0 TI MCU
Fediverse @lemmy.ml lemmy activity volume
Selfhosted @lemmy.world My take on Alpine as a platform for selfhosting
Ask Electronics @discuss.tchncs.de I want to learn designing IOT PCBs (with 2.4Ghz wireless)
Selfhosted @lemmy.world Home server rebuild automation workflow
Lemmy @lemmy.ml The minimalism of Jerboa app is unparalleled
Selfhosted @lemmy.world Ditching the VPN and port forwarding the selfhosted way
cool what was your hardware, and which qwen size you used? thanks